Machine Learning of Spatial Data (2021-09-12T00:00:00.000000Z)

TL;DR

It is argued that the properties of spatial data properties offered in the spatial observation matrix and in the learning algorithm itself offer the most promising prospects for the future of spatial machine learning.

Abstract

Properties of spatially explicit data are often ignored or inadequately handled in machine learning for spatial domains of application. At the same time, resources that would identify these properties and investigate their influence and methods to handle them in machine learning applications are lagging behind. In this survey of the literature, we seek to identify and discuss spatial properties of data that influence the performance of machine learning. We review some of the best practices in handling such properties in spatial domains and discuss their advantages and disadvantages. We recognize two broad strands in this literature. In the first, the properties of spatial data are developed in the spatial observation matrix without amending the substance of the learning algorithm; in the other, spatial data properties are handled in the learning algorithm itself. While the latter have been far less explored, we argue that they offer the most promising prospects for the future of spatial machine learning.

Authors

B. Nikparvar

1 papers

J. Thill

1 papers

TL;DR

Abstract

Authors

References200 items

Towards Robust Representations of Spatial Networks Using Graph Neural Networks

CrimeScape: Analysis of socio-spatial associations of urban residential motor vehicle theft.

Spatial-temporal graph neural network for traffic forecasting: An overview and open research issues

RLC-GNN: An Improved Deep Architecture for Spatial-Based Graph Neural Network with Application to Fraud Detection

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

Geographically weighted machine learning model for untangling spatial heterogeneity of type 2 diabetes mellitus (T2D) prevalence in the USA

VisualCheXbert: addressing the discrepancy between radiology report labels and image labels

GIS-based seismic vulnerability mapping: a comparison of artificial neural networks hybrid models

DeepGLEAM: a hybrid mechanistic and deep learning model for COVID-19 forecasting

RegNet: a neural network model for predicting regional desirability with VGI data

Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships

Spatial Aggregation Entropy: A Heterogeneity and Uncertainty Metric of Spatial Aggregation

PREDICTION OF SORGHUM BIOMASS USING TIME SERIES UAV-BASED HYPERSPECTRAL AND LIDAR DATA

Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics

Geographically and temporally neural network weighted regression for modeling spatiotemporal non-stationary relationships

How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey

Spatial heterogeneity of the cytosol revealed by machine learning-based 3D particle tracking

Representing Complex Evolving Spatial Networks: Geographic Network Automata

Domain Adaptation Based on Correlation Subspace Dynamic Distribution Alignment for Remote Sensing Image Scene Classification

Emergence of Visual Center-Periphery Spatial Organization in Deep Convolutional Neural Networks

Spatiotemporal Imputation of MAIAC AOD Using Deep Learning with Downscaling.

Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting

Improvement in Land Cover and Crop Classification based on Temporal Features Learning from Sentinel-2 Data Using Recurrent-Convolutional Neural Network (R-CNN)

Detecting regional dominant movement patterns in trajectory data with a convolutional neural network

Efficient Object Detection in Large Images Using Deep Reinforcement Learning

Spatial-Temporal Graph Attention Networks: A Deep Learning Approach for Traffic Forecasting

Graph-based Deep Learning in Natural Language Processing

Anisotropic characteristic of artificial light at night – Systematic investigation with VIIRS DNB multi-temporal observations

A deep learning architecture for semantic address matching

Fusion Of Low-And High-Level Features For Uav Hyperspectral Image Classification

A Survey on Spatial Prediction Methods

Importance of spatial predictor variable selection in machine learning applications - Moving from data reproduction to spatial prediction

EpiDeep: Exploiting Embeddings for Epidemic Forecasting

Data augmentation for intra-class imbalance with generative adversarial network

Learning from man or machine: Spatial fixed effects in urban econometrics

Artificial Intelligence Approaches

An Introduction to Variational Autoencoders

Machine learning for cross-gazetteer matching of natural features

Spatial interpolation using conditional generative adversarial neural networks

Assessment and modelling of urban road networks using Integrated Graph of Natural Road Network (a GIS-based approach)

A graph convolutional neural network for classification of building patterns using spatial vector data

A review of stochastic block models and extensions for graph clustering

Mesoscale Structures in World City Networks

Assessing the performance of 38 machine learning models: the case of land consumption rates in Bavaria, Germany

Joint Deep Learning for land cover and land use classification

Street-Frontage-Net: urban image classification using deep convolutional neural networks

Deep Learning on Graphs: A Survey

Using multi-scale and hierarchical deep convolutional features for 3D semantic classification of TLS point clouds

Fine-grained landuse characterization using ground-based pictures: a deep learning solution based on globally available data

Hyperparameter optimization of neural network-driven spatial models accelerated using cyber-enabled high-performance computing

An object-based convolutional neural network (OCNN) for urban land use classification

Understanding urban gentrification through machine learning

Unsupervised Learning

Machine Learning for Spatiotemporal Sequence Forecasting: A Survey

Spatial Deep Learning for Wireless Scheduling

Combining machine-learning topic models and spatiotemporal analysis of social media data for disaster footprint and damage assessment

IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium

Data augmentation for improving deep learning in image classification problem

Using Spatial Reinforcement Learning to Build Forest Wildfire Dynamics Models From Satellite Images

Visually-Enabled Active Deep Learning for (Geo) Text and Image Classification: A Review

Classifying airborne LiDAR point clouds via deep features learned by a multi-scale convolutional neural network

Toponym matching through deep neural networks

Heterogeneous Space–Time Artificial Neural Networks for Space–Time Series Prediction

PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs

How well does random forest analysis model deforestation and forest fragmentation in the Brazilian Atlantic forest?

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

Graph Attention Networks

A systematic study of the class imbalance problem in convolutional neural networks

Geographically Weighted Extreme Learning Machine: A Method for Space-Time Prediction: GWELM for Space-Time Prediction

Large-scale cost function learning for path planning using deep inverse reinforcement learning

A comprehensive evaluation of classification algorithms for coral reef habitat mapping: challenges related to quantity, quality, and impurity of training samples

Inductive Representation Learning on Large Graphs

Deep Projective 3D Semantic Segmentation

A Survey on Structure from Motion

Convolutional neural networks for hyperspectral image classification

Annals of the American association of geographers